[PATCH v6 net-next 1/3] filter: add Extended BPF interpreter and converter

From: Alexei Starovoitov
Date: Wed Mar 05 2014 - 22:31:00 EST

Extended BPF extends old BPF in the following ways:
- from 2 to 10 registers
Original BPF has two registers (A and X) and hidden frame pointer.
Extended BPF has ten registers and read-only frame pointer.
- from 32-bit registers to 64-bit registers
semantics of old 32-bit ALU operations are preserved via 32-bit
subregisters
- if (cond) jump_true; else jump_false;
old BPF insns are replaced with:
if (cond) jump_true; /* else fallthrough */
- adds signed > and >= insns
- 16 4-byte stack slots for register spill-fill replaced with
up to 512 bytes of multi-use stack space
- introduces bpf_call insn and register passing convention for zero
overhead calls from/to other kernel functions (not part of this patch)
- adds arithmetic right shift insn
- adds swab32/swab64 insns
- adds atomic_add insn
- old tax/txa insns are replaced with 'mov dst,src' insn

Extended BPF is designed to be JITed with one to one mapping, which
allows GCC/LLVM backends to generate optimized BPF code that performs
almost as fast as natively compiled code

sk_convert_filter() remaps old style insns into extended:
'sock_filter' instructions are remapped on the fly to
'sock_filter_ext' extended instructions when
sysctl net.core.bpf_ext_enable=1

Old filter comes through sk_attach_filter() or sk_unattached_filter_create()
if (bpf_ext_enable) {
convert to new
sk_chk_filter() - check old bpf
use sk_run_filter_ext() - new interpreter
} else {
sk_chk_filter() - check old bpf
if (bpf_jit_enable)
use old jit
else
use sk_run_filter() - old interpreter
}

sk_run_filter_ext() interpreter is noticeably faster
than sk_run_filter() for two reasons:

1.fall-through jumps
Old BPF jump instructions are forced to go either 'true' or 'false'
branch which causes branch-miss penalty.
Extended BPF jump instructions have one branch and fall-through,
which fit CPU branch predictor logic better.
'perf stat' shows drastic difference for branch-misses.

2.jump-threaded implementation of interpreter vs switch statement
Instead of single tablejump at the top of 'switch' statement, GCC will
generate multiple tablejump instructions, which helps CPU branch predictor

Performance of two BPF filters generated by libpcap was measured
on x86_64, i386 and arm32.

fprog #1 is taken from Documentation/networking/filter.txt:
tcpdump -i eth0 port 22 -dd

fprog #2 is taken from 'man tcpdump':
tcpdump -i eth0 'tcp port 22 and (((ip[2:2] - ((ip[0]&0xf)<<2)) -
((tcp[12]&0xf0)>>2)) != 0)' -dd

Other libpcap programs have similar performance differences.

Raw performance data from BPF micro-benchmark:
SK_RUN_FILTER on same SKB (cache-hit) or 10k SKBs (cache-miss)
time in nsec per call, smaller is better
--x86_64--
fprog #1 fprog #1 fprog #2 fprog #2
cache-hit cache-miss cache-hit cache-miss
old BPF 90 101 192 202
ext BPF 31 71 47 97
old BPF jit 12 34 17 44
ext BPF jit TBD

--i386--
fprog #1 fprog #1 fprog #2 fprog #2
cache-hit cache-miss cache-hit cache-miss
old BPF 107 136 227 252
ext BPF 40 119 69 172

--arm32--
fprog #1 fprog #1 fprog #2 fprog #2
cache-hit cache-miss cache-hit cache-miss
old BPF 202 300 475 540
ext BPF 139 270 296 470
old BPF jit 26 182 37 202
new BPF jit TBD

Tested with trinify BPF fuzzer

Future work:

0. add bpf/ebpf testsuite to tools/testing/selftests/net/bpf

1. add extended BPF JIT for x86_64

2. add inband old/new demux and extended BPF verifier, so that new programs
can be loaded through old sk_attach_filter() and sk_unattached_filter_create()
interfaces

3. tracing filters systemtap-like with extended BPF

4. OVS with extended BPF

5. nftables with extended BPF

Signed-off-by: Alexei Starovoitov <ast@xxxxxxxxxxxx>
Acked-by: Hagen Paul Pfeifer <hagen@xxxxxxxx>
Reviewed-by: Daniel Borkmann <dborkman@xxxxxxxxxx>
---
include/linux/filter.h | 6 +-
include/linux/netdevice.h | 1 +
include/uapi/linux/filter.h | 33 +-
net/core/filter.c | 801 ++++++++++++++++++++++++++++++++++++++++++-
net/core/sysctl_net_core.c | 7 +
5 files changed, 826 insertions(+), 22 deletions(-)

diff --git a/include/linux/filter.h b/include/linux/filter.h
index e568c8ef896b..beaba8580862 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -52,7 +52,11 @@ extern int sk_detach_filter(struct sock *sk);
extern int sk_chk_filter(struct sock_filter *filter, unsigned int flen);
extern int sk_get_filter(struct sock *sk, struct sock_filter __user *filter, unsigned len);
extern void sk_decode_filter(struct sock_filter *filt, struct sock_filter *to);
+int sk_convert_filter(struct sock_filter *old_prog, int len,
+ struct sock_filter_ext *new_prog, int *p_new_len);
+unsigned int sk_run_filter_ext(void *ctx, const struct sock_filter_ext *insn);

+#define SK_RUN_FILTER(FILTER, SKB) (*FILTER->bpf_func)(SKB, FILTER->insns)
#ifdef CONFIG_BPF_JIT
#include <stdarg.h>
#include <linux/linkage.h>
@@ -70,7 +74,6 @@ static inline void bpf_jit_dump(unsigned int flen, unsigned int proglen,
print_hex_dump(KERN_ERR, "JIT code: ", DUMP_PREFIX_OFFSET,
16, 1, image, proglen, false);
}
-#define SK_RUN_FILTER(FILTER, SKB) (*FILTER->bpf_func)(SKB, FILTER->insns)
#else
#include <linux/slab.h>
static inline void bpf_jit_compile(struct sk_filter *fp)
@@ -80,7 +83,6 @@ static inline void bpf_jit_free(struct sk_filter *fp)
{
kfree(fp);
}
-#define SK_RUN_FILTER(FILTER, SKB) sk_run_filter(SKB, FILTER->insns)
#endif

static inline int bpf_tell_extensions(void)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 1a869488b8ae..2c13d000389c 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3054,6 +3054,7 @@ extern int netdev_max_backlog;
extern int netdev_tstamp_prequeue;
extern int weight_p;
extern int bpf_jit_enable;
+extern int bpf_ext_enable;

bool netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev);
struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev,
diff --git a/include/uapi/linux/filter.h b/include/uapi/linux/filter.h
index 8eb9ccaa5b48..4e98fe16ba88 100644
--- a/include/uapi/linux/filter.h
+++ b/include/uapi/linux/filter.h
@@ -1,5 +1,6 @@
/*
* Linux Socket Filter Data Structures
+ * Extended BPF is Copyright (c) 2011-2014, PLUMgrid, http://plumgrid.com
*/

#ifndef _UAPI__LINUX_FILTER_H__
@@ -19,7 +20,7 @@
* Try and keep these values and structures similar to BSD, especially
* the BPF code definitions which need to match so you can share filters
*/
-
+
struct sock_filter { /* Filter block */
__u16 code; /* Actual filter code */
__u8 jt; /* Jump true */
@@ -27,6 +28,14 @@ struct sock_filter { /* Filter block */
__u32 k; /* Generic multiuse field */
};

+struct sock_filter_ext {
+ __u8 code; /* opcode */
+ __u8 a_reg:4; /* dest register */
+ __u8 x_reg:4; /* source register */
+ __s16 off; /* signed offset */
+ __s32 imm; /* signed immediate constant */
+};
+
struct sock_fprog { /* Required for SO_ATTACH_FILTER. */
unsigned short len; /* Number of filter blocks */
struct sock_filter __user *filter;
@@ -45,12 +54,14 @@ struct sock_fprog { /* Required for SO_ATTACH_FILTER. */
#define BPF_JMP 0x05
#define BPF_RET 0x06
#define BPF_MISC 0x07
+#define BPF_ALU64 0x07

/* ld/ldx fields */
#define BPF_SIZE(code) ((code) & 0x18)
#define BPF_W 0x00
#define BPF_H 0x08
#define BPF_B 0x10
+#define BPF_DW 0x18
#define BPF_MODE(code) ((code) & 0xe0)
#define BPF_IMM 0x00
#define BPF_ABS 0x20
@@ -58,6 +69,7 @@ struct sock_fprog { /* Required for SO_ATTACH_FILTER. */
#define BPF_MEM 0x60
#define BPF_LEN 0x80
#define BPF_MSH 0xa0
+#define BPF_XADD 0xc0 /* exclusive add */

/* alu/jmp fields */
#define BPF_OP(code) ((code) & 0xf0)
@@ -68,16 +80,24 @@ struct sock_fprog { /* Required for SO_ATTACH_FILTER. */
#define BPF_OR 0x40
#define BPF_AND 0x50
#define BPF_LSH 0x60
-#define BPF_RSH 0x70
+#define BPF_RSH 0x70 /* logical shift right */
#define BPF_NEG 0x80
#define BPF_MOD 0x90
#define BPF_XOR 0xa0
+#define BPF_MOV 0xb0 /* mov reg to reg */
+#define BPF_ARSH 0xc0 /* sign extending arithmetic shift right */
+#define BPF_BSWAP32 0xd0 /* swap lower 4 bytes of 64-bit register */
+#define BPF_BSWAP64 0xe0 /* swap all 8 bytes of 64-bit register */

#define BPF_JA 0x00
-#define BPF_JEQ 0x10
-#define BPF_JGT 0x20
-#define BPF_JGE 0x30
-#define BPF_JSET 0x40
+#define BPF_JEQ 0x10 /* jump == */
+#define BPF_JGT 0x20 /* GT is unsigned '>', JA in x86 */
+#define BPF_JGE 0x30 /* GE is unsigned '>=', JAE in x86 */
+#define BPF_JSET 0x40 /* if (A & X) */
+#define BPF_JNE 0x50 /* jump != */
+#define BPF_JSGT 0x60 /* SGT is signed '>', GT in x86 */
+#define BPF_JSGE 0x70 /* SGE is signed '>=', GE in x86 */
+#define BPF_CALL 0x80 /* function call */
#define BPF_SRC(code) ((code) & 0x08)
#define BPF_K 0x00
#define BPF_X 0x08
@@ -134,5 +154,4 @@ struct sock_fprog { /* Required for SO_ATTACH_FILTER. */
#define SKF_NET_OFF (-0x100000)
#define SKF_LL_OFF (-0x200000)

-
#endif /* _UAPI__LINUX_FILTER_H__ */
diff --git a/net/core/filter.c b/net/core/filter.c
index ad30d626a5bd..d04156e88a90 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1,5 +1,6 @@
/*
* Linux Socket Filter - Kernel level socket filtering
+ * Extended BPF is Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
*
* Author:
* Jay Schulist <jschlst@xxxxxxxxx>
@@ -40,6 +41,8 @@
#include <linux/seccomp.h>
#include <linux/if_vlan.h>

+int bpf_ext_enable __read_mostly;
+
/* No hurry in this branch
*
* Exported for the bpf jit load helper.
@@ -399,6 +402,7 @@ load_b:
}

return 0;
+#undef K
}
EXPORT_SYMBOL(sk_run_filter);

@@ -637,6 +641,10 @@ void sk_filter_release_rcu(struct rcu_head *rcu)
{
struct sk_filter *fp = container_of(rcu, struct sk_filter, rcu);

+ if ((void *)fp->bpf_func == (void *)sk_run_filter_ext)
+ /* arch specific jit_free are expecting this value */
+ fp->bpf_func = sk_run_filter;
+
bpf_jit_free(fp);
}
EXPORT_SYMBOL(sk_filter_release_rcu);
@@ -655,6 +663,81 @@ static int __sk_prepare_filter(struct sk_filter *fp)
return 0;
}

+static int sk_prepare_filter_ext(struct sk_filter **pfp,
+ struct sock_fprog *fprog, struct sock *sk)
+{
+ unsigned int fsize = sizeof(struct sock_filter) * fprog->len;
+ struct sock_filter *old_prog;
+ unsigned int sk_fsize;
+ struct sk_filter *fp;
+ int new_len;
+ int err;
+
+ /* store old program into buffer, since chk_filter will remap opcodes */
+ old_prog = kmalloc(fsize, GFP_KERNEL);
+ if (!old_prog)
+ return -ENOMEM;
+
+ if (sk) {
+ if (copy_from_user(old_prog, fprog->filter, fsize)) {
+ err = -EFAULT;
+ goto free_prog;
+ }
+ } else {
+ memcpy(old_prog, fprog->filter, fsize);
+ }
+
+ /* calculate bpf_ext program length */
+ err = sk_convert_filter(fprog->filter, fprog->len, NULL, &new_len);
+ if (err)
+ goto free_prog;
+
+ sk_fsize = sk_filter_size(new_len);
+ /* allocate sk_filter to store bpf_ext program */
+ if (sk)
+ fp = sock_kmalloc(sk, sk_fsize, GFP_KERNEL);
+ else
+ fp = kmalloc(sk_fsize, GFP_KERNEL);
+ if (!fp) {
+ err = -ENOMEM;
+ goto free_prog;
+ }
+
+ /* remap sock_filter insns into sock_filter_ext insns */
+ err = sk_convert_filter(old_prog, fprog->len,
+ (struct sock_filter_ext *)fp->insns, &new_len);
+ if (err)
+ /* 2nd sk_convert_filter() can fail only if it fails
+ * to allocate memory, remapping must succeed
+ */
+ goto free_fp;
+
+ /* now chk_filter can overwrite old_prog while checking */
+ err = sk_chk_filter(old_prog, fprog->len);
+ if (err)
+ goto free_fp;
+
+ /* discard old prog */
+ kfree(old_prog);
+
+ atomic_set(&fp->refcnt, 1);
+ fp->len = new_len;
+
+ /* sock_filter_ext insns must be executed by sk_run_filter_ext */
+ fp->bpf_func = (typeof(fp->bpf_func))sk_run_filter_ext;
+
+ *pfp = fp;
+ return 0;
+free_fp:
+ if (sk)
+ sock_kfree_s(sk, fp, sk_fsize);
+ else
+ kfree(fp);
+free_prog:
+ kfree(old_prog);
+ return err;
+}
+
/**
* sk_unattached_filter_create - create an unattached filter
* @fprog: the filter program
@@ -676,6 +759,9 @@ int sk_unattached_filter_create(struct sk_filter **pfp,
if (fprog->filter == NULL)
return -EINVAL;

+ if (bpf_ext_enable)
+ return sk_prepare_filter_ext(pfp, fprog, NULL);
+
fp = kmalloc(sk_filter_size(fprog->len), GFP_KERNEL);
if (!fp)
return -ENOMEM;
@@ -726,21 +812,27 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
if (fprog->filter == NULL)
return -EINVAL;

- fp = sock_kmalloc(sk, sk_fsize, GFP_KERNEL);
- if (!fp)
- return -ENOMEM;
- if (copy_from_user(fp->insns, fprog->filter, fsize)) {
- sock_kfree_s(sk, fp, sk_fsize);
- return -EFAULT;
- }
+ if (bpf_ext_enable) {
+ err = sk_prepare_filter_ext(&fp, fprog, sk);
+ if (err)
+ return err;
+ } else {
+ fp = sock_kmalloc(sk, sk_fsize, GFP_KERNEL);
+ if (!fp)
+ return -ENOMEM;
+ if (copy_from_user(fp->insns, fprog->filter, fsize)) {
+ sock_kfree_s(sk, fp, sk_fsize);
+ return -EFAULT;
+ }

- atomic_set(&fp->refcnt, 1);
- fp->len = fprog->len;
+ atomic_set(&fp->refcnt, 1);
+ fp->len = fprog->len;

- err = __sk_prepare_filter(fp);
- if (err) {
- sk_filter_uncharge(sk, fp);
- return err;
+ err = __sk_prepare_filter(fp);
+ if (err) {
+ sk_filter_uncharge(sk, fp);
+ return err;
+ }
}

old_fp = rcu_dereference_protected(sk->sk_filter,
@@ -882,3 +974,686 @@ out:
release_sock(sk);
return ret;
}
+
+/**
+ * sk_convert_filter - convert filter program
+ * @old_prog: the filter program
+ * @len: the length of filter program
+ * @new_prog: buffer where converted program will be stored
+ * @p_new_len: pointer to store length of converted program
+ *
+ * remap 'sock_filter' style BPF instruction set to 'sock_filter_ext' style
+ *
+ * first, call sk_convert_filter(old_prog, len, NULL, &new_len) to calculate new
+ * program length in one pass
+ *
+ * then new_prog = kmalloc(sizeof(struct sock_filter_ext) * new_len);
+ *
+ * and call it again: sk_convert_filter(old_prog, len, new_prog, &new_len);
+ * to remap in two passes: 1st pass finds new jump offsets, 2nd pass remaps
+ */
+int sk_convert_filter(struct sock_filter *old_prog, int len,
+ struct sock_filter_ext *new_prog, int *p_new_len)
+{
+ struct sock_filter_ext *new_insn;
+ struct sock_filter *fp;
+ int *addrs = NULL;
+ int new_len = 0;
+ int pass = 0;
+ int tgt, i;
+ u8 bpf_src;
+
+ if (len <= 0 || len >= BPF_MAXINSNS)
+ return -EINVAL;
+
+ if (new_prog) {
+ addrs = kzalloc(len * sizeof(*addrs), GFP_KERNEL);
+ if (!addrs)
+ return -ENOMEM;
+ }
+
+do_pass:
+ new_insn = new_prog;
+ fp = old_prog;
+ for (i = 0; i < len; fp++, i++) {
+ struct sock_filter_ext tmp_insns[3] = {};
+ struct sock_filter_ext *insn = tmp_insns;
+
+ if (addrs)
+ addrs[i] = new_insn - new_prog;
+
+ switch (fp->code) {
+ /* all arithmetic insns and skb loads map as-is */
+ case BPF_ALU | BPF_ADD | BPF_X:
+ case BPF_ALU | BPF_ADD | BPF_K:
+ case BPF_ALU | BPF_SUB | BPF_X:
+ case BPF_ALU | BPF_SUB | BPF_K:
+ case BPF_ALU | BPF_AND | BPF_X:
+ case BPF_ALU | BPF_AND | BPF_K:
+ case BPF_ALU | BPF_OR | BPF_X:
+ case BPF_ALU | BPF_OR | BPF_K:
+ case BPF_ALU | BPF_LSH | BPF_X:
+ case BPF_ALU | BPF_LSH | BPF_K:
+ case BPF_ALU | BPF_RSH | BPF_X:
+ case BPF_ALU | BPF_RSH | BPF_K:
+ case BPF_ALU | BPF_XOR | BPF_X:
+ case BPF_ALU | BPF_XOR | BPF_K:
+ case BPF_ALU | BPF_MUL | BPF_X:
+ case BPF_ALU | BPF_MUL | BPF_K:
+ case BPF_ALU | BPF_DIV | BPF_X:
+ case BPF_ALU | BPF_DIV | BPF_K:
+ case BPF_ALU | BPF_MOD | BPF_X:
+ case BPF_ALU | BPF_MOD | BPF_K:
+ case BPF_ALU | BPF_NEG:
+ case BPF_LD | BPF_ABS | BPF_W:
+ case BPF_LD | BPF_ABS | BPF_H:
+ case BPF_LD | BPF_ABS | BPF_B:
+ case BPF_LD | BPF_IND | BPF_W:
+ case BPF_LD | BPF_IND | BPF_H:
+ case BPF_LD | BPF_IND | BPF_B:
+ insn->code = fp->code;
+ insn->a_reg = 6;
+ insn->x_reg = 7;
+ insn->imm = fp->k;
+ break;
+
+ /* jump opcodes map as-is, but offsets need adjustment */
+ case BPF_JMP | BPF_JA:
+ tgt = i + fp->k + 1;
+ insn->code = fp->code;
+#define EMIT_JMP \
+ do { \
+ if (tgt >= len || tgt < 0) \
+ goto err; \
+ insn->off = addrs ? addrs[tgt] - addrs[i] - 1 : 0; \
+ /* adjust pc relative offset for 2nd or 3rd insn */ \
+ insn->off -= insn - tmp_insns; \
+ } while (0)
+
+ EMIT_JMP;
+ break;
+
+ case BPF_JMP | BPF_JEQ | BPF_K:
+ case BPF_JMP | BPF_JEQ | BPF_X:
+ case BPF_JMP | BPF_JSET | BPF_K:
+ case BPF_JMP | BPF_JSET | BPF_X:
+ case BPF_JMP | BPF_JGT | BPF_K:
+ case BPF_JMP | BPF_JGT | BPF_X:
+ case BPF_JMP | BPF_JGE | BPF_K:
+ case BPF_JMP | BPF_JGE | BPF_X:
+ if (BPF_SRC(fp->code) == BPF_K &&
+ (int)fp->k < 0) {
+ /* extended BPF immediates are signed,
+ * zero extend immediate into tmp register
+ * and use it in compare insn
+ */
+ insn->code = BPF_ALU | BPF_MOV | BPF_K;
+ insn->a_reg = 2;
+ insn->imm = fp->k;
+ insn++;
+
+ insn->a_reg = 6;
+ insn->x_reg = 2;
+ bpf_src = BPF_X;
+ } else {
+ insn->a_reg = 6;
+ insn->x_reg = 7;
+ insn->imm = fp->k;
+ bpf_src = BPF_SRC(fp->code);
+ }
+ /* common case where 'jump_false' is next insn */
+ if (fp->jf == 0) {
+ insn->code = BPF_JMP | BPF_OP(fp->code) |
+ bpf_src;
+ tgt = i + fp->jt + 1;
+ EMIT_JMP;
+ break;
+ }
+ /* convert JEQ into JNE when 'jump_true' is next insn */
+ if (fp->jt == 0 && BPF_OP(fp->code) == BPF_JEQ) {
+ insn->code = BPF_JMP | BPF_JNE | bpf_src;
+ tgt = i + fp->jf + 1;
+ EMIT_JMP;
+ break;
+ }
+ /* other jumps are mapped into two insns: Jxx and JA */
+ tgt = i + fp->jt + 1;
+ insn->code = BPF_JMP | BPF_OP(fp->code) | bpf_src;
+ EMIT_JMP;
+
+ insn++;
+ insn->code = BPF_JMP | BPF_JA;
+ tgt = i + fp->jf + 1;
+ EMIT_JMP;
+ break;
+
+ /* ldxb 4*([14]&0xf) is remaped into 3 insns */
+ case BPF_LDX | BPF_MSH | BPF_B:
+ insn->code = BPF_LD | BPF_ABS | BPF_B;
+ insn->a_reg = 7;
+ insn->imm = fp->k;
+
+ insn++;
+ insn->code = BPF_ALU | BPF_AND | BPF_K;
+ insn->a_reg = 7;
+ insn->imm = 0xf;
+
+ insn++;
+ insn->code = BPF_ALU | BPF_LSH | BPF_K;
+ insn->a_reg = 7;
+ insn->imm = 2;
+ break;
+
+ /* RET_K, RET_A are remaped into 2 insns */
+ case BPF_RET | BPF_A:
+ case BPF_RET | BPF_K:
+ insn->code = BPF_ALU | BPF_MOV |
+ (BPF_RVAL(fp->code) == BPF_K ? BPF_K : BPF_X);
+ insn->a_reg = 0;
+ insn->x_reg = 6;
+ insn->imm = fp->k;
+
+ insn++;
+ insn->code = BPF_RET | BPF_K;
+ break;
+
+ /* store to stack */
+ case BPF_ST:
+ case BPF_STX:
+ insn->code = BPF_STX | BPF_MEM | BPF_W;
+ insn->a_reg = 10;
+ insn->x_reg = fp->code == BPF_ST ? 6 : 7;
+ insn->off = -(BPF_MEMWORDS - fp->k) * 4;
+ break;
+
+ /* load from stack */
+ case BPF_LD | BPF_MEM:
+ case BPF_LDX | BPF_MEM:
+ insn->code = BPF_LDX | BPF_MEM | BPF_W;
+ insn->a_reg = BPF_CLASS(fp->code) == BPF_LD ? 6 : 7;
+ insn->x_reg = 10;
+ insn->off = -(BPF_MEMWORDS - fp->k) * 4;
+ break;
+
+ /* A = K or X = K */
+ case BPF_LD | BPF_IMM:
+ case BPF_LDX | BPF_IMM:
+ insn->code = BPF_ALU | BPF_MOV | BPF_K;
+ insn->a_reg = BPF_CLASS(fp->code) == BPF_LD ? 6 : 7;
+ insn->imm = fp->k;
+ break;
+
+ /* X = A */
+ case BPF_MISC | BPF_TAX:
+ insn->code = BPF_ALU64 | BPF_MOV | BPF_X;
+ insn->a_reg = 7;
+ insn->x_reg = 6;
+ break;
+
+ /* A = X */
+ case BPF_MISC | BPF_TXA:
+ insn->code = BPF_ALU64 | BPF_MOV | BPF_X;
+ insn->a_reg = 6;
+ insn->x_reg = 7;
+ break;
+
+ /* A = skb->len or X = skb->len */
+ case BPF_LD | BPF_W | BPF_LEN:
+ case BPF_LDX | BPF_W | BPF_LEN:
+ insn->code = BPF_LDX | BPF_MEM | BPF_W;
+ insn->a_reg = BPF_CLASS(fp->code) == BPF_LD ? 6 : 7;
+ insn->x_reg = 1;
+ insn->off = offsetof(struct sk_buff, len);
+ break;
+
+ /* access seccomp_data fields */
+ case BPF_LDX | BPF_ABS | BPF_W:
+ insn->code = BPF_LDX | BPF_MEM | BPF_W;
+ insn->a_reg = 6;
+ insn->x_reg = 1;
+ insn->off = fp->k;
+ break;
+
+ default:
+ /* pr_err("unknown opcode %02x\n", fp->code); */
+ goto err;
+ }
+
+ insn++;
+ if (new_prog) {
+ memcpy(new_insn, tmp_insns,
+ sizeof(*insn) * (insn - tmp_insns));
+ }
+ new_insn += insn - tmp_insns;
+ }
+
+ if (!new_prog) {
+ /* only calculating new length */
+ *p_new_len = new_insn - new_prog;
+ return 0;
+ }
+
+ pass++;
+ if (new_len != new_insn - new_prog) {
+ new_len = new_insn - new_prog;
+ if (pass > 2)
+ goto err;
+ goto do_pass;
+ }
+ kfree(addrs);
+ if (*p_new_len != new_len)
+ /* inconsistent new program length */
+ pr_err("sk_convert_filter() usage error\n");
+ return 0;
+err:
+ kfree(addrs);
+ return -EINVAL;
+}
+
+/**
+ * sk_run_filter_ext - run an extended filter
+ * @ctx: buffer to run the filter on
+ * @insn: filter to apply
+ *
+ * Decode and execute extended BPF instructions.
+ * @ctx is the data we are operating on.
+ * @filter is the array of filter instructions.
+ */
+notrace u32 sk_run_filter_ext(void *ctx, const struct sock_filter_ext *insn)
+{
+ u64 stack[64];
+ u64 regs[16];
+ void *ptr;
+ u64 tmp;
+ int off;
+
+#ifdef __x86_64
+#define LOAD_IMM /**/
+#define K insn->imm
+#else
+#define LOAD_IMM (K = insn->imm)
+ s32 K = insn->imm;
+#endif
+
+#define A regs[insn->a_reg]
+#define X regs[insn->x_reg]
+
+#define CONT ({insn++; LOAD_IMM; goto select_insn; })
+#define CONT_JMP ({insn++; LOAD_IMM; goto select_insn; })
+/* some compilers may need help:
+ * #define CONT_JMP ({insn++; LOAD_IMM; goto *jumptable[insn->code]; })
+ */
+
+ static const void *jumptable[256] = {
+ [0 ... 255] = &&default_label,
+#define DL(A, B, C) [A|B|C] = &&A##_##B##_##C,
+ DL(BPF_ALU, BPF_ADD, BPF_X)
+ DL(BPF_ALU, BPF_ADD, BPF_K)
+ DL(BPF_ALU, BPF_SUB, BPF_X)
+ DL(BPF_ALU, BPF_SUB, BPF_K)
+ DL(BPF_ALU, BPF_AND, BPF_X)
+ DL(BPF_ALU, BPF_AND, BPF_K)
+ DL(BPF_ALU, BPF_OR, BPF_X)
+ DL(BPF_ALU, BPF_OR, BPF_K)
+ DL(BPF_ALU, BPF_LSH, BPF_X)
+ DL(BPF_ALU, BPF_LSH, BPF_K)
+ DL(BPF_ALU, BPF_RSH, BPF_X)
+ DL(BPF_ALU, BPF_RSH, BPF_K)
+ DL(BPF_ALU, BPF_XOR, BPF_X)
+ DL(BPF_ALU, BPF_XOR, BPF_K)
+ DL(BPF_ALU, BPF_MUL, BPF_X)
+ DL(BPF_ALU, BPF_MUL, BPF_K)
+ DL(BPF_ALU, BPF_MOV, BPF_X)
+ DL(BPF_ALU, BPF_MOV, BPF_K)
+ DL(BPF_ALU, BPF_DIV, BPF_X)
+ DL(BPF_ALU, BPF_DIV, BPF_K)
+ DL(BPF_ALU, BPF_MOD, BPF_X)
+ DL(BPF_ALU, BPF_MOD, BPF_K)
+ DL(BPF_ALU64, BPF_ADD, BPF_X)
+ DL(BPF_ALU64, BPF_ADD, BPF_K)
+ DL(BPF_ALU64, BPF_SUB, BPF_X)
+ DL(BPF_ALU64, BPF_SUB, BPF_K)
+ DL(BPF_ALU64, BPF_AND, BPF_X)
+ DL(BPF_ALU64, BPF_AND, BPF_K)
+ DL(BPF_ALU64, BPF_OR, BPF_X)
+ DL(BPF_ALU64, BPF_OR, BPF_K)
+ DL(BPF_ALU64, BPF_LSH, BPF_X)
+ DL(BPF_ALU64, BPF_LSH, BPF_K)
+ DL(BPF_ALU64, BPF_RSH, BPF_X)
+ DL(BPF_ALU64, BPF_RSH, BPF_K)
+ DL(BPF_ALU64, BPF_XOR, BPF_X)
+ DL(BPF_ALU64, BPF_XOR, BPF_K)
+ DL(BPF_ALU64, BPF_MUL, BPF_X)
+ DL(BPF_ALU64, BPF_MUL, BPF_K)
+ DL(BPF_ALU64, BPF_MOV, BPF_X)
+ DL(BPF_ALU64, BPF_MOV, BPF_K)
+ DL(BPF_ALU64, BPF_ARSH, BPF_X)
+ DL(BPF_ALU64, BPF_ARSH, BPF_K)
+ DL(BPF_ALU64, BPF_DIV, BPF_X)
+ DL(BPF_ALU64, BPF_DIV, BPF_K)
+ DL(BPF_ALU64, BPF_MOD, BPF_X)
+ DL(BPF_ALU64, BPF_MOD, BPF_K)
+ DL(BPF_ALU64, BPF_BSWAP32, BPF_X)
+ DL(BPF_ALU64, BPF_BSWAP64, BPF_X)
+ DL(BPF_ALU, BPF_NEG, 0)
+ DL(BPF_JMP, BPF_CALL, 0)
+ DL(BPF_JMP, BPF_JA, 0)
+ DL(BPF_JMP, BPF_JEQ, BPF_X)
+ DL(BPF_JMP, BPF_JEQ, BPF_K)
+ DL(BPF_JMP, BPF_JNE, BPF_X)
+ DL(BPF_JMP, BPF_JNE, BPF_K)
+ DL(BPF_JMP, BPF_JGT, BPF_X)
+ DL(BPF_JMP, BPF_JGT, BPF_K)
+ DL(BPF_JMP, BPF_JGE, BPF_X)
+ DL(BPF_JMP, BPF_JGE, BPF_K)
+ DL(BPF_JMP, BPF_JSGT, BPF_X)
+ DL(BPF_JMP, BPF_JSGT, BPF_K)
+ DL(BPF_JMP, BPF_JSGE, BPF_X)
+ DL(BPF_JMP, BPF_JSGE, BPF_K)
+ DL(BPF_JMP, BPF_JSET, BPF_X)
+ DL(BPF_JMP, BPF_JSET, BPF_K)
+ DL(BPF_STX, BPF_MEM, BPF_B)
+ DL(BPF_STX, BPF_MEM, BPF_H)
+ DL(BPF_STX, BPF_MEM, BPF_W)
+ DL(BPF_STX, BPF_MEM, BPF_DW)
+ DL(BPF_ST, BPF_MEM, BPF_B)
+ DL(BPF_ST, BPF_MEM, BPF_H)
+ DL(BPF_ST, BPF_MEM, BPF_W)
+ DL(BPF_ST, BPF_MEM, BPF_DW)
+ DL(BPF_LDX, BPF_MEM, BPF_B)
+ DL(BPF_LDX, BPF_MEM, BPF_H)
+ DL(BPF_LDX, BPF_MEM, BPF_W)
+ DL(BPF_LDX, BPF_MEM, BPF_DW)
+ DL(BPF_STX, BPF_XADD, BPF_W)
+#ifdef CONFIG_64BIT
+ DL(BPF_STX, BPF_XADD, BPF_DW)
+#endif
+ DL(BPF_LD, BPF_ABS, BPF_W)
+ DL(BPF_LD, BPF_ABS, BPF_H)
+ DL(BPF_LD, BPF_ABS, BPF_B)
+ DL(BPF_LD, BPF_IND, BPF_W)
+ DL(BPF_LD, BPF_IND, BPF_H)
+ DL(BPF_LD, BPF_IND, BPF_B)
+ DL(BPF_RET, BPF_K, 0)
+#undef DL
+ };
+
+ regs[10/* BPF R10 */] = (u64)(ulong)&stack[64];
+ regs[1/* BPF R1 */] = (u64)(ulong)ctx;
+
+ /* execute 1st insn */
+select_insn:
+ goto *jumptable[insn->code];
+
+ /* ALU */
+#define ALU(OPCODE, OP) \
+ BPF_ALU64_##OPCODE##_BPF_X: \
+ A = A OP X; \
+ CONT; \
+ BPF_ALU_##OPCODE##_BPF_X: \
+ A = (u32)A OP (u32)X; \
+ CONT; \
+ BPF_ALU64_##OPCODE##_BPF_K: \
+ A = A OP K; \
+ CONT; \
+ BPF_ALU_##OPCODE##_BPF_K: \
+ A = (u32)A OP (u32)K; \
+ CONT;
+
+ ALU(BPF_ADD, +)
+ ALU(BPF_SUB, -)
+ ALU(BPF_AND, &)
+ ALU(BPF_OR, |)
+ ALU(BPF_LSH, <<)
+ ALU(BPF_RSH, >>)
+ ALU(BPF_XOR, ^)
+ ALU(BPF_MUL, *)
+#undef ALU
+
+BPF_ALU_BPF_NEG_0:
+ A = (u32)-A;
+ CONT;
+BPF_ALU_BPF_MOV_BPF_X:
+ A = (u32)X;
+ CONT;
+BPF_ALU_BPF_MOV_BPF_K:
+ A = (u32)K;
+ CONT;
+BPF_ALU64_BPF_MOV_BPF_X:
+ A = X;
+ CONT;
+BPF_ALU64_BPF_MOV_BPF_K:
+ A = K;
+ CONT;
+BPF_ALU64_BPF_ARSH_BPF_X:
+ (*(s64 *) &A) >>= X;
+ CONT;
+BPF_ALU64_BPF_ARSH_BPF_K:
+ (*(s64 *) &A) >>= K;
+ CONT;
+BPF_ALU64_BPF_MOD_BPF_X:
+ tmp = A;
+ if (X)
+ A = do_div(tmp, X);
+ CONT;
+BPF_ALU_BPF_MOD_BPF_X:
+ tmp = (u32)A;
+ if (X)
+ A = do_div(tmp, (u32)X);
+ CONT;
+BPF_ALU64_BPF_MOD_BPF_K:
+ tmp = A;
+ if (K)
+ A = do_div(tmp, K);
+ CONT;
+BPF_ALU_BPF_MOD_BPF_K:
+ tmp = (u32)A;
+ if (K)
+ A = do_div(tmp, (u32)K);
+ CONT;
+BPF_ALU64_BPF_DIV_BPF_X:
+ if (X)
+ do_div(A, X);
+ CONT;
+BPF_ALU_BPF_DIV_BPF_X:
+ tmp = (u32)A;
+ if (X)
+ do_div(tmp, (u32)X);
+ A = (u32)tmp;
+ CONT;
+BPF_ALU64_BPF_DIV_BPF_K:
+ if (K)
+ do_div(A, K);
+ CONT;
+BPF_ALU_BPF_DIV_BPF_K:
+ tmp = (u32)A;
+ if (K)
+ do_div(tmp, (u32)K);
+ A = (u32)tmp;
+ CONT;
+BPF_ALU64_BPF_BSWAP32_BPF_X:
+ A = swab32(A);
+ CONT;
+BPF_ALU64_BPF_BSWAP64_BPF_X:
+ A = swab64(A);
+ CONT;
+
+ /* CALL */
+BPF_JMP_BPF_CALL_0:
+ return 0; /* not implemented yet */
+
+ /* JMP */
+BPF_JMP_BPF_JA_0:
+ insn += insn->off;
+ CONT;
+BPF_JMP_BPF_JEQ_BPF_X:
+ if (A == X) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+BPF_JMP_BPF_JEQ_BPF_K:
+ if (A == K) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+BPF_JMP_BPF_JNE_BPF_X:
+ if (A != X) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+BPF_JMP_BPF_JNE_BPF_K:
+ if (A != K) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+BPF_JMP_BPF_JGT_BPF_X:
+ if (A > X) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+BPF_JMP_BPF_JGT_BPF_K:
+ if (A > K) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+BPF_JMP_BPF_JGE_BPF_X:
+ if (A >= X) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+BPF_JMP_BPF_JGE_BPF_K:
+ if (A >= K) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+BPF_JMP_BPF_JSGT_BPF_X:
+ if (((s64)A) > ((s64)X)) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+BPF_JMP_BPF_JSGT_BPF_K:
+ if (((s64)A) > ((s64)K)) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+BPF_JMP_BPF_JSGE_BPF_X:
+ if (((s64)A) >= ((s64)X)) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+BPF_JMP_BPF_JSGE_BPF_K:
+ if (((s64)A) >= ((s64)K)) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+BPF_JMP_BPF_JSET_BPF_X:
+ if (A & X) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+BPF_JMP_BPF_JSET_BPF_K:
+ if (A & K) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+
+ /* STX and ST and LDX*/
+#define LDST(SIZEOP, SIZE) \
+ BPF_STX_BPF_MEM_##SIZEOP: \
+ *(SIZE *)(ulong)(A + insn->off) = X; \
+ CONT; \
+ BPF_ST_BPF_MEM_##SIZEOP: \
+ *(SIZE *)(ulong)(A + insn->off) = K; \
+ CONT; \
+ BPF_LDX_BPF_MEM_##SIZEOP: \
+ A = *(SIZE *)(ulong)(X + insn->off); \
+ CONT;
+
+ LDST(BPF_B, u8)
+ LDST(BPF_H, u16)
+ LDST(BPF_W, u32)
+ LDST(BPF_DW, u64)
+#undef LDST
+
+BPF_STX_BPF_XADD_BPF_W: /* lock xadd *(u32 *)(A + insn->off) += X */
+ atomic_add((u32)X, (atomic_t *)(ulong)(A + insn->off));
+ CONT;
+#ifdef CONFIG_64BIT
+BPF_STX_BPF_XADD_BPF_DW: /* lock xadd *(u64 *)(A + insn->off) += X */
+ atomic64_add((u64)X, (atomic64_t *)(ulong)(A + insn->off));
+ CONT;
+#endif
+
+BPF_LD_BPF_ABS_BPF_W: /* A = *(u32 *)(SKB + K) */
+ off = K;
+load_word:
+ ptr = load_pointer((struct sk_buff *)ctx, off, 4, &tmp);
+ if (likely(ptr != NULL)) {
+ A = get_unaligned_be32(ptr);
+ CONT;
+ }
+ return 0;
+
+BPF_LD_BPF_ABS_BPF_H: /* A = *(u16 *)(SKB + K) */
+ off = K;
+load_half:
+ ptr = load_pointer((struct sk_buff *)ctx, off, 2, &tmp);
+ if (likely(ptr != NULL)) {
+ A = get_unaligned_be16(ptr);
+ CONT;
+ }
+ return 0;
+
+BPF_LD_BPF_ABS_BPF_B: /* A = *(u8 *)(SKB + K) */
+ off = K;
+load_byte:
+ ptr = load_pointer((struct sk_buff *)ctx, off, 1, &tmp);
+ if (likely(ptr != NULL)) {
+ A = *(u8 *)ptr;
+ CONT;
+ }
+ return 0;
+
+BPF_LD_BPF_IND_BPF_W: /* A = *(u32 *)(SKB + X + K) */
+ off = K + X;
+ goto load_word;
+
+BPF_LD_BPF_IND_BPF_H: /* A = *(u16 *)(SKB + X + K) */
+ off = K + X;
+ goto load_half;
+
+BPF_LD_BPF_IND_BPF_B: /* A = *(u8 *)(SKB + X + K) */
+ off = K + X;
+ goto load_byte;
+
+ /* RET */
+BPF_RET_BPF_K_0:
+ return regs[0/* R0 */];
+
+default_label:
+ /* sk_chk_filter_ext() and sk_convert_filter() guarantee
+ * that we never reach here
+ */
+ WARN_RATELIMIT(1, "unknown opcode %02x\n", insn->code);
+ return 0;
+#undef CONT
+#undef A
+#undef X
+#undef K
+#undef LOAD_IMM
+}
+EXPORT_SYMBOL(sk_run_filter_ext);
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index cf9cd13509a7..e1b979312588 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -273,6 +273,13 @@ static struct ctl_table net_core_table[] = {
},
#endif
{
+ .procname = "bpf_ext_enable",
+ .data = &bpf_ext_enable,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
+ {
.procname = "netdev_tstamp_prequeue",
.data = &netdev_tstamp_prequeue,
.maxlen = sizeof(int),
--
1.7.9.5

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/